Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1492 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.4649. Min Range: -4.4649

Max Act: 4.4649. Min Act: -0.1700

Data Index: 8698063 (Open Web Text)

Max Activating Token Index: 897

Text #1

Max Range: 4.4649. Min Range: -4.4649

Max Act: 4.3921. Min Act: -0.1700

Data Index: 1984118 (Open Web Text)

Max Activating Token Index: 102

Text #2

Max Range: 4.4649. Min Range: -4.4649

Max Act: 4.3148. Min Act: -0.1700

Data Index: 7166091 (Open Web Text)

Max Activating Token Index: 1008

Text #3

Max Range: 4.4649. Min Range: -4.4649

Max Act: 4.2869. Min Act: -0.1700

Data Index: 7165953 (Open Web Text)

Max Activating Token Index: 609

Text #4

Max Range: 4.4649. Min Range: -4.4649

Max Act: 4.2803. Min Act: -0.1700

Data Index: 2140857 (Open Web Text)

Max Activating Token Index: 126

Text #5

Max Range: 4.4649. Min Range: -4.4649

Max Act: 4.2743. Min Act: -0.1700

Data Index: 470521 (Open Web Text)

Max Activating Token Index: 337

Text #6

Max Range: 4.4649. Min Range: -4.4649

Max Act: 4.2061. Min Act: -0.1700

Data Index: 4188035 (Open Web Text)

Max Activating Token Index: 84

Text #7

Max Range: 4.4649. Min Range: -4.4649

Max Act: 4.1679. Min Act: -0.1700

Data Index: 1061728 (Open Web Text)

Max Activating Token Index: 681

Text #8

Max Range: 4.4649. Min Range: -4.4649

Max Act: 4.2392. Min Act: -0.1700

Data Index: 8186156 (Open Web Text)

Max Activating Token Index: 682

Text #9

Max Range: 4.4649. Min Range: -4.4649

Max Act: 4.1940. Min Act: -0.1700

Data Index: 8526034 (Open Web Text)

Max Activating Token Index: 847

Text #10

Max Range: 4.4649. Min Range: -4.4649

Max Act: 4.2020. Min Act: -0.1700

Data Index: 6665406 (Open Web Text)

Max Activating Token Index: 862

Text #11

Max Range: 4.4649. Min Range: -4.4649

Max Act: 4.1745. Min Act: -0.1700

Data Index: 5891013 (Open Web Text)

Max Activating Token Index: 556

Text #12

Max Range: 4.4649. Min Range: -4.4649

Max Act: 4.1753. Min Act: -0.1700

Data Index: 6232476 (Open Web Text)

Max Activating Token Index: 965

Text #13

Max Range: 4.4649. Min Range: -4.4649

Max Act: 4.1902. Min Act: -0.1700

Data Index: 2009229 (Open Web Text)

Max Activating Token Index: 598

Text #14

Max Range: 4.4649. Min Range: -4.4649

Max Act: 4.1676. Min Act: -0.1700

Data Index: 3066657 (Open Web Text)

Max Activating Token Index: 922

Text #15

Max Range: 4.4649. Min Range: -4.4649

Max Act: 4.1379. Min Act: -0.1700

Data Index: 6051952 (Open Web Text)

Max Activating Token Index: 579

Text #16

Max Range: 4.4649. Min Range: -4.4649

Max Act: 4.1670. Min Act: -0.1700

Data Index: 814486 (Open Web Text)

Max Activating Token Index: 740

Text #17

Max Range: 4.4649. Min Range: -4.4649

Max Act: 4.1589. Min Act: -0.1700

Data Index: 8017647 (Open Web Text)

Max Activating Token Index: 718

Text #18

Max Range: 4.4649. Min Range: -4.4649

Max Act: 4.1445. Min Act: -0.1700

Data Index: 2273561 (Open Web Text)

Max Activating Token Index: 121

Text #19

Max Range: 4.4649. Min Range: -4.4649

Max Act: 4.1495. Min Act: -0.1700

Data Index: 5109028 (Open Web Text)

Max Activating Token Index: 794